[CI] Restructure vLLM-Omni Test Layout, Fixture Scope, and Support Modules (#2620)

Signed-off-by: wangyu <410167048@qq.com>
This commit is contained in:
wangyu authored and GitHub committed 2026-04-20 14:23:42 +08:00
1 parent 0393c58533
commit 8a9add1c81
130 files changed
+4549 -5306

No files matched your search

+3 -7
View File
@@ -7,18 +7,15 @@ import pytest
from vllm import SamplingParams
from vllm.inputs import PromptType
# Side-effect import: registers QWEN2_5_OMNI_THINKER_ONLY_PIPELINE in the
# pipeline registry so the materialized deploy overlay below can select it
# via its top-level ``pipeline:`` field.
import vllm_omni.model_executor.models.qwen2_5_omni.pipeline # noqa: F401, E402
from tests.utils import get_deploy_config_path, hardware_test
from tests.helpers.mark import hardware_test
from tests.helpers.stage_config import get_deploy_config_path
from vllm_omni.entrypoints.async_omni import AsyncOmni
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
SEED = 42
# Single-stage thinker-only deploy, materialized from tests.utils._CI_OVERLAYS.
# Single-stage thinker-only deploy, materialized from tests.helpers.stage_config._CI_OVERLAYS.
stage_config = get_deploy_config_path("ci/qwen2_5_omni_thinker_only.yaml")
model = "Qwen/Qwen2.5-Omni-7B"
@@ -64,7 +61,6 @@ async def generate(
@pytest.mark.core_model
@pytest.mark.omni
@pytest.mark.real_hf_config
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards=1)
@pytest.mark.asyncio
async def test_abort():